Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-03 03:21:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: fix thread/block count in quantized cpy kernel launches (#26731)

Browse Source 
* CUDA: fix thread/block count in quantized cpy kernel launches

* tests: add uneven block count cpy case
This commit is contained in:
Rafail Giavrimis
2026-08-08 05:40:04 +01:00
committed by GitHub
parent 3653e6d6d5
commit 69bf643791
2 changed files with 25 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-backend-ops.cpp
+3
View File
@@ -8576,6 +8576,9 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_cpy(type_src, type_dst, {256, 2, 3, 4}, {-1,-1,-1,-1}, {1, 0, 2, 3})); // cpy not-contiguous
}
}
// quant block count not a multiple of the kernel block size
test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_Q4_0, {96, 1, 1, 1}));
test_cases.emplace_back(new test_cpy(GGML_TYPE_Q4_0, GGML_TYPE_F32, {96, 1, 1, 1}));
test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_I32, {256, 2, 3, 4}));
test_cases.emplace_back(new test_cpy(GGML_TYPE_F32, GGML_TYPE_I32, {256, 2, 3, 4}, {-1,-1,-1,-1}, {1, 0, 2, 3}));
test_cases.emplace_back(new test_cpy(GGML_TYPE_I32, GGML_TYPE_F32, {256, 2, 3, 4}));